Commit
•
9429c9d
1
Parent(s):
5575e14
Training in progress, step 1000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +363 -3
- last-checkpoint/training_args.bin +1 -1
- pytorch_model.bin +1 -1
- runs/Feb08_05-23-30_74bc69b4becb/1675839811.8360035/events.out.tfevents.1675839811.74bc69b4becb.290.7 +3 -0
- runs/Feb08_05-23-30_74bc69b4becb/events.out.tfevents.1675836783.74bc69b4becb.290.4 +2 -2
- runs/Feb08_05-23-30_74bc69b4becb/events.out.tfevents.1675839811.74bc69b4becb.290.6 +3 -0
- runs/Feb08_07-03-50_74bc69b4becb/1675839843.9712958/events.out.tfevents.1675839843.74bc69b4becb.290.9 +3 -0
- runs/Feb08_07-03-50_74bc69b4becb/events.out.tfevents.1675839843.74bc69b4becb.290.8 +3 -0
- training_args.bin +1 -1
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4115013
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e6d34c98f3791a3faa787960bb3a83c840754af10c0771225b4641fc4876571
|
| 3 |
size 4115013
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2329702453
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f05ed8aadfcb52667b608ea047bd58bd244bcded7029940cddd4dbb9db150031
|
| 3 |
size 2329702453
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14575
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d2ff9b22bc08f364a63197a3c58a1819f82aa700f010edb44f336a90cc9fb87
|
| 3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 627
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9a7ec99b1bee8f2349cfd0142e944266b1486c4d9544af390e2e3f4a57486848
|
| 3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -366,11 +366,371 @@
|
|
| 366 |
"eval_samples_per_second": 0.237,
|
| 367 |
"eval_steps_per_second": 0.237,
|
| 368 |
"step": 500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 369 |
}
|
| 370 |
],
|
| 371 |
"max_steps": 3542,
|
| 372 |
"num_train_epochs": 7,
|
| 373 |
-
"total_flos":
|
| 374 |
"trial_name": null,
|
| 375 |
"trial_params": null
|
| 376 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.9744791024534583,
|
| 5 |
+
"global_step": 1000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 366 |
"eval_samples_per_second": 0.237,
|
| 367 |
"eval_steps_per_second": 0.237,
|
| 368 |
"step": 500
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 1.01,
|
| 372 |
+
"learning_rate": 0.00043916570104287375,
|
| 373 |
+
"loss": 0.279,
|
| 374 |
+
"step": 510
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.03,
|
| 378 |
+
"learning_rate": 0.00043771726535341834,
|
| 379 |
+
"loss": 0.272,
|
| 380 |
+
"step": 520
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 1.05,
|
| 384 |
+
"learning_rate": 0.00043626882966396293,
|
| 385 |
+
"loss": 0.2272,
|
| 386 |
+
"step": 530
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 1.07,
|
| 390 |
+
"learning_rate": 0.0004348203939745076,
|
| 391 |
+
"loss": 0.2495,
|
| 392 |
+
"step": 540
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 1.09,
|
| 396 |
+
"learning_rate": 0.00043337195828505216,
|
| 397 |
+
"loss": 0.1965,
|
| 398 |
+
"step": 550
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 1.11,
|
| 402 |
+
"learning_rate": 0.00043192352259559675,
|
| 403 |
+
"loss": 0.2364,
|
| 404 |
+
"step": 560
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 1.13,
|
| 408 |
+
"learning_rate": 0.0004304750869061414,
|
| 409 |
+
"loss": 0.2478,
|
| 410 |
+
"step": 570
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 1.15,
|
| 414 |
+
"learning_rate": 0.000429026651216686,
|
| 415 |
+
"loss": 0.2046,
|
| 416 |
+
"step": 580
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.17,
|
| 420 |
+
"learning_rate": 0.0004275782155272306,
|
| 421 |
+
"loss": 0.2661,
|
| 422 |
+
"step": 590
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 1.19,
|
| 426 |
+
"learning_rate": 0.0004261297798377752,
|
| 427 |
+
"loss": 0.2041,
|
| 428 |
+
"step": 600
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 1.19,
|
| 432 |
+
"eval_loss": 0.9551488757133484,
|
| 433 |
+
"eval_rouge1": 0.09038461538461538,
|
| 434 |
+
"eval_rouge2": 0.05051948051948052,
|
| 435 |
+
"eval_rougeL": 0.09679487179487178,
|
| 436 |
+
"eval_rougeLsum": 0.09871794871794871,
|
| 437 |
+
"eval_runtime": 89.0139,
|
| 438 |
+
"eval_samples_per_second": 0.225,
|
| 439 |
+
"eval_steps_per_second": 0.225,
|
| 440 |
+
"step": 600
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 1.21,
|
| 444 |
+
"learning_rate": 0.0004246813441483198,
|
| 445 |
+
"loss": 0.2816,
|
| 446 |
+
"step": 610
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 1.22,
|
| 450 |
+
"learning_rate": 0.0004232329084588644,
|
| 451 |
+
"loss": 0.1904,
|
| 452 |
+
"step": 620
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 1.24,
|
| 456 |
+
"learning_rate": 0.00042178447276940904,
|
| 457 |
+
"loss": 0.21,
|
| 458 |
+
"step": 630
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.26,
|
| 462 |
+
"learning_rate": 0.0004203360370799537,
|
| 463 |
+
"loss": 0.1662,
|
| 464 |
+
"step": 640
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 1.28,
|
| 468 |
+
"learning_rate": 0.0004188876013904983,
|
| 469 |
+
"loss": 0.3052,
|
| 470 |
+
"step": 650
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 1.3,
|
| 474 |
+
"learning_rate": 0.0004174391657010429,
|
| 475 |
+
"loss": 0.1744,
|
| 476 |
+
"step": 660
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 1.32,
|
| 480 |
+
"learning_rate": 0.0004159907300115875,
|
| 481 |
+
"loss": 0.288,
|
| 482 |
+
"step": 670
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 1.34,
|
| 486 |
+
"learning_rate": 0.0004145422943221321,
|
| 487 |
+
"loss": 0.2303,
|
| 488 |
+
"step": 680
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 1.36,
|
| 492 |
+
"learning_rate": 0.00041309385863267674,
|
| 493 |
+
"loss": 0.2866,
|
| 494 |
+
"step": 690
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 1.38,
|
| 498 |
+
"learning_rate": 0.00041164542294322133,
|
| 499 |
+
"loss": 0.238,
|
| 500 |
+
"step": 700
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.38,
|
| 504 |
+
"eval_loss": 0.9423090219497681,
|
| 505 |
+
"eval_rouge1": 0.1,
|
| 506 |
+
"eval_rouge2": 0.07291666666666667,
|
| 507 |
+
"eval_rougeL": 0.1,
|
| 508 |
+
"eval_rougeLsum": 0.10333333333333335,
|
| 509 |
+
"eval_runtime": 88.0456,
|
| 510 |
+
"eval_samples_per_second": 0.227,
|
| 511 |
+
"eval_steps_per_second": 0.227,
|
| 512 |
+
"step": 700
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 1.4,
|
| 516 |
+
"learning_rate": 0.0004101969872537659,
|
| 517 |
+
"loss": 0.2342,
|
| 518 |
+
"step": 710
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 1.42,
|
| 522 |
+
"learning_rate": 0.00040874855156431057,
|
| 523 |
+
"loss": 0.2716,
|
| 524 |
+
"step": 720
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 1.44,
|
| 528 |
+
"learning_rate": 0.00040730011587485516,
|
| 529 |
+
"loss": 0.2453,
|
| 530 |
+
"step": 730
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 1.46,
|
| 534 |
+
"learning_rate": 0.00040585168018539974,
|
| 535 |
+
"loss": 0.2313,
|
| 536 |
+
"step": 740
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 1.48,
|
| 540 |
+
"learning_rate": 0.0004044032444959444,
|
| 541 |
+
"loss": 0.2306,
|
| 542 |
+
"step": 750
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 1.5,
|
| 546 |
+
"learning_rate": 0.000402954808806489,
|
| 547 |
+
"loss": 0.1773,
|
| 548 |
+
"step": 760
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 1.52,
|
| 552 |
+
"learning_rate": 0.00040150637311703357,
|
| 553 |
+
"loss": 0.1957,
|
| 554 |
+
"step": 770
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 1.54,
|
| 558 |
+
"learning_rate": 0.0004000579374275782,
|
| 559 |
+
"loss": 0.2758,
|
| 560 |
+
"step": 780
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 1.56,
|
| 564 |
+
"learning_rate": 0.0003986095017381228,
|
| 565 |
+
"loss": 0.2649,
|
| 566 |
+
"step": 790
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 1.58,
|
| 570 |
+
"learning_rate": 0.0003971610660486675,
|
| 571 |
+
"loss": 0.275,
|
| 572 |
+
"step": 800
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 1.58,
|
| 576 |
+
"eval_loss": 0.9273136258125305,
|
| 577 |
+
"eval_rouge1": 0.14666666666666667,
|
| 578 |
+
"eval_rouge2": 0.10977272727272727,
|
| 579 |
+
"eval_rougeL": 0.15038461538461537,
|
| 580 |
+
"eval_rougeLsum": 0.15153846153846154,
|
| 581 |
+
"eval_runtime": 87.8017,
|
| 582 |
+
"eval_samples_per_second": 0.228,
|
| 583 |
+
"eval_steps_per_second": 0.228,
|
| 584 |
+
"step": 800
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.6,
|
| 588 |
+
"learning_rate": 0.0003957126303592121,
|
| 589 |
+
"loss": 0.2102,
|
| 590 |
+
"step": 810
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 1.62,
|
| 594 |
+
"learning_rate": 0.0003942641946697567,
|
| 595 |
+
"loss": 0.2146,
|
| 596 |
+
"step": 820
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 1.64,
|
| 600 |
+
"learning_rate": 0.0003928157589803013,
|
| 601 |
+
"loss": 0.1918,
|
| 602 |
+
"step": 830
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 1.66,
|
| 606 |
+
"learning_rate": 0.0003913673232908459,
|
| 607 |
+
"loss": 0.2512,
|
| 608 |
+
"step": 840
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 1.68,
|
| 612 |
+
"learning_rate": 0.0003899188876013905,
|
| 613 |
+
"loss": 0.2499,
|
| 614 |
+
"step": 850
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 1.7,
|
| 618 |
+
"learning_rate": 0.00038847045191193515,
|
| 619 |
+
"loss": 0.228,
|
| 620 |
+
"step": 860
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 1.72,
|
| 624 |
+
"learning_rate": 0.00038702201622247974,
|
| 625 |
+
"loss": 0.2507,
|
| 626 |
+
"step": 870
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.74,
|
| 630 |
+
"learning_rate": 0.0003855735805330243,
|
| 631 |
+
"loss": 0.1735,
|
| 632 |
+
"step": 880
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 1.76,
|
| 636 |
+
"learning_rate": 0.00038412514484356897,
|
| 637 |
+
"loss": 0.2752,
|
| 638 |
+
"step": 890
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 1.78,
|
| 642 |
+
"learning_rate": 0.00038267670915411356,
|
| 643 |
+
"loss": 0.2379,
|
| 644 |
+
"step": 900
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 1.78,
|
| 648 |
+
"eval_loss": 0.9023244976997375,
|
| 649 |
+
"eval_rouge1": 0.1,
|
| 650 |
+
"eval_rouge2": 0.08333333333333333,
|
| 651 |
+
"eval_rougeL": 0.1,
|
| 652 |
+
"eval_rougeLsum": 0.1,
|
| 653 |
+
"eval_runtime": 80.7798,
|
| 654 |
+
"eval_samples_per_second": 0.248,
|
| 655 |
+
"eval_steps_per_second": 0.248,
|
| 656 |
+
"step": 900
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 1.8,
|
| 660 |
+
"learning_rate": 0.00038122827346465815,
|
| 661 |
+
"loss": 0.1993,
|
| 662 |
+
"step": 910
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 1.82,
|
| 666 |
+
"learning_rate": 0.0003797798377752028,
|
| 667 |
+
"loss": 0.2058,
|
| 668 |
+
"step": 920
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.84,
|
| 672 |
+
"learning_rate": 0.0003783314020857474,
|
| 673 |
+
"loss": 0.2675,
|
| 674 |
+
"step": 930
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 1.86,
|
| 678 |
+
"learning_rate": 0.00037688296639629197,
|
| 679 |
+
"loss": 0.1928,
|
| 680 |
+
"step": 940
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 1.88,
|
| 684 |
+
"learning_rate": 0.0003754345307068366,
|
| 685 |
+
"loss": 0.1903,
|
| 686 |
+
"step": 950
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 1.9,
|
| 690 |
+
"learning_rate": 0.00037398609501738126,
|
| 691 |
+
"loss": 0.1967,
|
| 692 |
+
"step": 960
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 1.92,
|
| 696 |
+
"learning_rate": 0.00037253765932792585,
|
| 697 |
+
"loss": 0.2044,
|
| 698 |
+
"step": 970
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 1.94,
|
| 702 |
+
"learning_rate": 0.0003710892236384705,
|
| 703 |
+
"loss": 0.2027,
|
| 704 |
+
"step": 980
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 1.95,
|
| 708 |
+
"learning_rate": 0.0003696407879490151,
|
| 709 |
+
"loss": 0.25,
|
| 710 |
+
"step": 990
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 1.97,
|
| 714 |
+
"learning_rate": 0.00036819235225955967,
|
| 715 |
+
"loss": 0.2896,
|
| 716 |
+
"step": 1000
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 1.97,
|
| 720 |
+
"eval_loss": 0.9184179306030273,
|
| 721 |
+
"eval_rouge1": 0.19,
|
| 722 |
+
"eval_rouge2": 0.1,
|
| 723 |
+
"eval_rougeL": 0.18893939393939393,
|
| 724 |
+
"eval_rougeLsum": 0.19848484848484846,
|
| 725 |
+
"eval_runtime": 81.9559,
|
| 726 |
+
"eval_samples_per_second": 0.244,
|
| 727 |
+
"eval_steps_per_second": 0.244,
|
| 728 |
+
"step": 1000
|
| 729 |
}
|
| 730 |
],
|
| 731 |
"max_steps": 3542,
|
| 732 |
"num_train_epochs": 7,
|
| 733 |
+
"total_flos": 2.429607036460032e+16,
|
| 734 |
"trial_name": null,
|
| 735 |
"trial_params": null
|
| 736 |
}
|
last-checkpoint/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3643
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:660f1225e692fbbda687422d3532879d3c116f23c4ac0ae767265d9fdf03511c
|
| 3 |
size 3643
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2329702453
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f05ed8aadfcb52667b608ea047bd58bd244bcded7029940cddd4dbb9db150031
|
| 3 |
size 2329702453
|
runs/Feb08_05-23-30_74bc69b4becb/1675839811.8360035/events.out.tfevents.1675839811.74bc69b4becb.290.7
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:68b19e19e49a5585b95a1cf2ea41121eed756dbef1dea86815786e8e86ad97ca
|
| 3 |
+
size 5952
|
runs/Feb08_05-23-30_74bc69b4becb/events.out.tfevents.1675836783.74bc69b4becb.290.4
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:af8ff3619c5e7959921946e1c8f07ab19f490618fe1eadf1ad8ab63dae6cadde
|
| 3 |
+
size 10523
|
runs/Feb08_05-23-30_74bc69b4becb/events.out.tfevents.1675839811.74bc69b4becb.290.6
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:44e57fd7a05f538e83f65e0f7f6d3626b5c64c0e3f74a9f494de3d08115edafc
|
| 3 |
+
size 4234
|
runs/Feb08_07-03-50_74bc69b4becb/1675839843.9712958/events.out.tfevents.1675839843.74bc69b4becb.290.9
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ee98b68b79f929f357d2c12a4a37be65cdda2e91c16f092582b4b1f874266e74
|
| 3 |
+
size 5952
|
runs/Feb08_07-03-50_74bc69b4becb/events.out.tfevents.1675839843.74bc69b4becb.290.8
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:07efd7031be8ab155496121fd04b911227f322b0793e4124f1b3bfb2e678b8b4
|
| 3 |
+
size 14454
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3643
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:660f1225e692fbbda687422d3532879d3c116f23c4ac0ae767265d9fdf03511c
|
| 3 |
size 3643
|